Over the last four decades, the amazing success of deep learning has been driven by the use of Stochastic Gradient Descent (SGD) as the main optimization technique. The default implementation for the computation of the gradient for SGD is backpropagation, which, with its variations, is used to this day in almost all computer implementations. From the perspective of neuroscientists, however, the consensus is that backpropagation is unlikely to be used by the brain. Though several alternatives have been discussed, none is so far supported by experimental evidence. Here we propose a circuit for updating the weights in a network that is biologically plausible, works as well as backpropagation, and leads to verifiable predictions about the anatomy and the physiology of a characteristic motif of four plastic synapses between ascending and descending cortical streams. A key prediction of our proposal is a surprising property of self-assembly of the basic circuit, emerging from initial random connectivity and heterosynaptic plasticity rules.

翻译：在过去的四十年里，深度学习的惊人成功主要得益于使用随机梯度下降作为核心优化技术。计算SGD梯度的默认实现方法是反向传播，其各种变体至今仍用于几乎所有的计算机实现。然而，从神经科学家的视角来看，学界普遍认为大脑不太可能使用反向传播。尽管已有多种替代方案被讨论，但迄今为止尚无任何一种得到实验证据的支持。本文提出了一种用于更新网络权重的回路，该回路在生物学上是可信的，其性能与反向传播相当，并能产生关于上行与下行皮层流之间四个可塑性突触特征性基序的解剖学和生理学的可验证预测。我们方案的一个关键预测是基本回路具有一种令人惊讶的自组装特性，该特性源于初始随机连接性和异突触可塑性规则。